Semantic based learning of syntax in an autonomous robot

Matthew McClain, Stephen Levinson

Research output: Contribution to journalArticle

Abstract

It is the goal of the Language Acquisition Group at the University of Illinois at Urbana-Champaign (LAR-UIUC) to build a robot that is able to learn language as well as humans through embodied sensori-motor interaction with the physical world. This paper proposes cognitive structures to enable an autonomous robot to learn the syntax of two-word sentences using its understanding of lexical semantics. A production rule of syntax in Chomsky Normal Form will be explicitly represented using a hidden Markov Model. Results of robotic experiments show that these models can learn representations of syntax in this form and that they can be used to produce novel sentences.

Original languageEnglish (US)
Pages (from-to)321-346
Number of pages26
JournalInternational Journal of Humanoid Robotics
Volume4
Issue number2
DOIs
StatePublished - Jun 1 2007

Fingerprint

Semantics
Robots
Hidden Markov models
Robotics
Experiments

Keywords

  • Machine language acquisition
  • Robotics
  • Semantics
  • Syntax

ASJC Scopus subject areas

  • Mechanical Engineering
  • Artificial Intelligence

Cite this

Semantic based learning of syntax in an autonomous robot. / McClain, Matthew; Levinson, Stephen.

In: International Journal of Humanoid Robotics, Vol. 4, No. 2, 01.06.2007, p. 321-346.

Research output: Contribution to journalArticle

@article{019aa28ab35c4ad9bdaa776a0d0bc530,
title = "Semantic based learning of syntax in an autonomous robot",
abstract = "It is the goal of the Language Acquisition Group at the University of Illinois at Urbana-Champaign (LAR-UIUC) to build a robot that is able to learn language as well as humans through embodied sensori-motor interaction with the physical world. This paper proposes cognitive structures to enable an autonomous robot to learn the syntax of two-word sentences using its understanding of lexical semantics. A production rule of syntax in Chomsky Normal Form will be explicitly represented using a hidden Markov Model. Results of robotic experiments show that these models can learn representations of syntax in this form and that they can be used to produce novel sentences.",
keywords = "Machine language acquisition, Robotics, Semantics, Syntax",
author = "Matthew McClain and Stephen Levinson",
year = "2007",
month = "6",
day = "1",
doi = "10.1142/S0219843607001023",
language = "English (US)",
volume = "4",
pages = "321--346",
journal = "International Journal of Humanoid Robotics",
issn = "0219-8436",
publisher = "World Scientific Publishing Co. Pte Ltd",
number = "2",

}

TY - JOUR

T1 - Semantic based learning of syntax in an autonomous robot

AU - McClain, Matthew

AU - Levinson, Stephen

PY - 2007/6/1

Y1 - 2007/6/1

N2 - It is the goal of the Language Acquisition Group at the University of Illinois at Urbana-Champaign (LAR-UIUC) to build a robot that is able to learn language as well as humans through embodied sensori-motor interaction with the physical world. This paper proposes cognitive structures to enable an autonomous robot to learn the syntax of two-word sentences using its understanding of lexical semantics. A production rule of syntax in Chomsky Normal Form will be explicitly represented using a hidden Markov Model. Results of robotic experiments show that these models can learn representations of syntax in this form and that they can be used to produce novel sentences.

AB - It is the goal of the Language Acquisition Group at the University of Illinois at Urbana-Champaign (LAR-UIUC) to build a robot that is able to learn language as well as humans through embodied sensori-motor interaction with the physical world. This paper proposes cognitive structures to enable an autonomous robot to learn the syntax of two-word sentences using its understanding of lexical semantics. A production rule of syntax in Chomsky Normal Form will be explicitly represented using a hidden Markov Model. Results of robotic experiments show that these models can learn representations of syntax in this form and that they can be used to produce novel sentences.

KW - Machine language acquisition

KW - Robotics

KW - Semantics

KW - Syntax

UR - http://www.scopus.com/inward/record.url?scp=34447331673&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34447331673&partnerID=8YFLogxK

U2 - 10.1142/S0219843607001023

DO - 10.1142/S0219843607001023

M3 - Article

AN - SCOPUS:34447331673

VL - 4

SP - 321

EP - 346

JO - International Journal of Humanoid Robotics

JF - International Journal of Humanoid Robotics

SN - 0219-8436

IS - 2

ER -